[Feature] Multimodal Scheduler V1 #3019
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Thanks for your contribution! |
TBD1
reviewed
Jul 25, 2025
| // limitations under the License. | ||
|
|
||
| #include "paddle/extension.h" | ||
| #include <map> |
yuanlehome
reviewed
Jul 25, 2025
Comment on lines
151
to
152
| old_end_idx = request.num_computed_tokens | ||
| new_end_idx = old_end_idx + num_new_tokens |
Collaborator
There was a problem hiding this comment.
old/new，是不是换成prev/cur更好理解点
yuanlehome
reviewed
Jul 25, 2025
| return {out}; | ||
| } | ||
|
|
||
| PD_BUILD_OP(get_img_boundaries) |
Collaborator
There was a problem hiding this comment.
PD_BUILD_OP是不是没走pybind啊
Collaborator
Author
There was a problem hiding this comment.
这个算子用在服务上层，和推理引擎是异步的，不用也影响不大
Collaborator
|
Update fix according to #3071 |
rainyfly
approved these changes
Jul 30, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Background
Adapt Scheduler V1 for multimodality on the basis of #2928.
Perf
Near to Scheduler V0.
Effect
Config kv_cache_ratio is deprecated, and the
recovery stopissue will no longer occur in the multimodal service.How to enable
Set environment variable ENABLE_V1_KVCACHE_SCHEDULER to 1 to enable scheduler v1.
export ENABLE_V1_KVCACHE_SCHEDULER=1